Operator context scanning to support high segmentation rates for real time license plate recognition

Introducing high definition videos and images in object recognition has provided new possibilities in the field of intelligent image processing and pattern recognition. However, due to the large amount of information that needs to be processed, the computational costs are high, making the HD systems slow. To this end, a novel algorithm applied to sliding window analysis, namely Operator Context Scanning (OCS), is proposed and tested on the license plate detection module of a License Plate Recognition (LPR) system. In the LPR system, the OCS algorithm is applied on the Sliding Concentric Windows pixel operator and has been found to improve the LPR system’s performance in terms of speed by rapidly scanning input images focusing only on regions of interest, while at the same time it does not reduce the system effectiveness. Additionally, a novel characteristic is presented, namely, the context of the image based on a sliding windows operator. This characteristic helps to quickly categorize the environmental conditions upon which the input image was taken. The algorithm is tested on a data set that includes images of various resolutions, acquired under a variety of environmental conditions.     

Revisiting Zhang's 1D calibration algorithm

In recent years, the camera calibration using 1D patterns has been studied and improved by researchers all over the world. However, the progress in that area has been mainly in the sense of reducing the restrictions to the 1D pattern movement. On the other hand, the method's accuracy still demands improvements. In the present paper, the original technique proposed by Zhang is revisited and we demonstrate that the method's accuracy can be significantly improved, simply by analyzing and reformulating the problem. The numerical conditioning can be improved if a simple data normalization is performed. Furthermore, a non-linear solution based on the Partitioned Levenberg-Marquardt algorithm is proposed. That solution takes advantage of the problem's particular structure to reduce the computational complexity of the original method and to improve the accuracy. Tests using both synthetic and real images demonstrate that the calibration method using 1D patterns can be applied in practice, with accuracy comparable to other already traditional methods.     

Fast k most similar neighbor classifier for mixed data (tree k-MSN)

The k nearest neighbor (k-NN) classifier has been a widely used nonparametric technique in Pattern Recognition, because of its simplicity and good performance. In order to decide the class of a new prototype, the k-NN classifier performs an exhaustive comparison between the prototype to classify and the prototypes in the training set T. However, when T is large, the exhaustive comparison is expensive. For this reason, many fast k-NN classifiers have been developed, some of them are based on a tree structure, which is created during a preprocessing phase using the prototypes in T. Then, in a search phase, the tree is traversed to find the nearest neighbor. The speed up is obtained, while the exploration of some parts of the tree is avoided using pruning rules which are usually based on the triangle inequality. However, in soft sciences as Medicine, Geology, Sociology, etc., the prototypes are usually described by numerical and categorical attributes (mixed data), and sometimes the comparison function for computing the similarity between prototypes does not satisfy metric properties. Therefore, in this work an approximate fast k most similar neighbor classifier, for mixed data and similarity functions that do not satisfy metric properties, based on a tree structure (Tree k-MSN) is proposed. Some experiments with synthetic and real data are presented.     

Parametric estimation of affine deformations of planar shapes

We consider the estimation of affine transformations aligning a known 2D shape and its distorted observation. The classical way to solve this registration problem is to find correspondences between the shapes and then compute the transformation parameters from these landmarks. Here we propose a novel approach where the exact transformation is obtained as the solution of a polynomial system of equations. The method has been tested on synthetic as well as on real images and its robustness in the presence of segmentation errors and additive geometric noise has also been demonstrated. We have successfully applied the method for the registration of hip prosthesis X-ray images. The advantage of the proposed solution is that it is fast, easy to implement, has linear time complexity, works without established correspondences and provides an exact solution regardless of the magnitude of transformation.     

Skin detection for single images using dynamic skin color modeling

Up-to-date skin detection techniques use adaptive skin color modeling to overcome the varying skin color problem. Most methods for tracking skin regions in videos utilize the correlation between contiguous frames. This paper proposes a new approach for detecting skin in a single image. This approach uses a local skin model to shift a globally trained skin model to adapt the final skin model to the current image. Experimental results show that the proposed method can achieve better accuracy. Two improvements for speeding up the processing are also discussed.     

Analysis of multi-agent activity using petri nets

This paper presents the use of place/transition petri nets (PNs) for the recognition and evaluation of complex multi-agent activities. The PNs were built automatically from the activity templates that are routinely used by experts to encode domain-specific knowledge. The PNs were built in such a way that they encoded the complex temporal relations between the individual activity actions. We extended the original PN formalism to handle the propagation of evidence using net tokens. The evaluation of the spatial and temporal properties of the actions was carried out using trajectory-based action detectors and probabilistic models of the action durations. The presented approach was evaluated using several examples of real basketball activities. The obtained experimental results suggest that this approach can be used to determine the type of activity that a team has performed as well as the stage at which the activity ended.     

Local contrast enhancement and adaptive feature extraction for illumination-invariant face recognition

Recognizing human faces in various lighting conditions is quite a difficult problem. The problem becomes more difficult when face images are taken in extremely high dynamic range scenes. Most of the automatic face recognition systems assume that images are taken under well-controlled illumination. The face segmentation as well as recognition becomes much simpler under such a constrained condition. However, illumination control is not feasible when a surveillance system is installed in any location at will. Without compensating for uneven illumination, it is impossible to get a satisfactory recognition rate. In this paper, we propose an integrated system that first compensates uneven illumination through local contrast enhancement. Then the enhanced images are fed into a robust face recognition system which adaptively selects the most important features among all candidate features and performs classification by support vector machines (SVMs). The dimension of feature space as well as the selected types of features is customized for each hyperplane. Three face image databases, namely Yale, Yale Group B, and Extended Yale Group B, are used to evaluate performance. The experimental result shows that the proposed recognition system give superior results compared to recently published literatures.     

Recognition of handwritten Chinese characters by critical region analysis

The problem of recognizing offline handwritten Chinese characters has been investigated extensively. One difficulty is due to the existence of characters with very similar shapes. In this paper, we propose a “critical region analysis” technique which highlights the critical regions that distinguish one character from another similar character. The critical regions are identified automatically based on the output of the Fisher's discriminant. Additional features are extracted from these regions and contribute to the recognition process. By incorporating this technique into the character recognition system, a record high recognition rate of 99.53% on the ETL-9B database is obtained.     

Local normalized linear summation kernel for fast and robust recognition

Kernel-based methods are effective for object detection and recognition. However, the computational cost when using kernel functions is high, except when using linear kernels. To realize fast and robust recognition, we apply normalized linear kernels to local regions of a recognition target, and the kernel outputs are integrated by summation. This kernel is referred to as a local normalized linear summation kernel. Here, we show that kernel-based methods that employ local normalized linear summation kernels can be computed by a linear kernel of local normalized features. Thus, the computational cost of the kernel is nearly the same as that of a linear kernel and much lower than that of radial basis function (RBF) and polynomial kernels. The effectiveness of the proposed method is evaluated in face detection and recognition problems, and we confirm that our kernel provides higher accuracy with lower computational cost than RBF and polynomial kernels. In addition, our kernel is also robust to partial occlusion and shadows on faces since it is based on the summation of local kernels.